Triple
T37084978
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Casablanca-class escort carrier |
E918257
|
entity |
| Predicate | notableShipOfClass |
P3345
|
FINISHED |
| Object |
USS Casablanca (CVE-55)
USS Casablanca (CVE-55) was the lead ship of the U.S. Navy’s Casablanca-class escort carriers, serving as a prototype and namesake for the most numerous class of aircraft carriers ever built.
|
E2213036
|
NE FINISHED |
How this triple was built (3 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: USS Casablanca (CVE-55) | Statement: [Casablanca-class escort carrier, notableShipOfClass, USS Casablanca (CVE-55)]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: USS Casablanca (CVE-55) Triple: [Casablanca-class escort carrier, notableShipOfClass, USS Casablanca (CVE-55)]
Generated description
USS Casablanca (CVE-55) was the lead ship of the U.S. Navy’s Casablanca-class escort carriers, serving as a prototype and namesake for the most numerous class of aircraft carriers ever built.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableShipOfClass Context triple: [Casablanca-class escort carrier, notableShipOfClass, USS Casablanca (CVE-55)]
-
A.
notableShip
chosen
Indicates that there is a notable or significant ship associated with the subject entity.
-
B.
shipClass
Indicates the classification or type category to which a particular ship belongs.
-
C.
shipClassDeveloped
Indicates that a particular ship class was developed or designed by a specified entity (such as a country, organization, or manufacturer).
-
D.
fleetOrClass
Indicates that something belongs to, is part of, or is categorized under a particular fleet or class.
-
E.
isWarshipOf
Indicates that a given warship belongs to, is operated by, or is part of the naval forces of a specified country or organization.
- F. None of above.
Provenance (6 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69f76e9952b88190a6fe01ba01476520 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a037c8e2c648190a65fc9c7872861af |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a3efdc87fa08190b25f7ab8a395c100 |
completed | June 26, 2026, 10:31 p.m. |
| NEDg | Description generation | batch_6a3f444ba9ec8190bb6ad6b98d2f19f9 |
completed | June 27, 2026, 3:32 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a3f453d286481909c3f05d6af7dfeb7 |
completed | June 27, 2026, 3:36 a.m. |
| PD | Predicate disambiguation | batch_6a037a10036481909c71188b2a0e7f04 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:14 p.m.